Abstract: A method and program product includes scanning for at least one identification means of an object. An image of the object is captured. An identification associated with the image and the image are communicated to a training system. The training system is configured for at least training a neural network system with identifications and images to produce synaptic weights. Synaptic weights are received from the training system. A predicted identification from a captured image of an object is predicted. The predicting uses at least the synaptic weights.

Abstract: A machine learning innovation for point of sale systems is provided which includes a scanner component, which can scan at least one of the following codes: Barcode, QR code, RFID or any other new code and id, a camera component, which can get image or picture of objects, and a compute component with prediction algorithm to classify the object. The system also includes a method with prediction and learning capability that sends the classified labels to central controller or server. A central controller or server gathers classified labels and analyze and learn from classified labels information, and sends updated a scanner component, which can scan at least one of the codes.